Plotly

Data Summary

income <- read.csv("https://ecoleman451.github.io/ecoleman/w6/income_per_person.csv")

life <- read.csv("https://ecoleman451.github.io/ecoleman/w6/life_expectancy_years.csv")

# Reshape data set such that there are only three columns (Geo, Year, & Income)
new_income <- pivot_longer(income, cols = -geo, names_to = "year", values_to = "income")

new_life <- pivot_longer(life, cols = -geo, names_to = "year", values_to = "life.expectancy")

## Create new data set
LifeExpIncom <- merge(new_life, new_income, by = c("geo", "year"))

## Read in More Data
country <- read.csv("https://ecoleman451.github.io/ecoleman/w6/countries_total.csv")

pop <- read.csv("https://ecoleman451.github.io/ecoleman/w6/population_total.csv")

new_pop <- pivot_longer(pop, cols = -geo, names_to = "year", values_to = "population")

## Merge LifeExpIncom with Country
merged <- merge(LifeExpIncom, country, by.x = "geo", by.y = "name", all.x = TRUE)

## Merge Population with Merged Data
fin_data <- merge(new_pop, merged, by = c("geo", "year"), all.x = TRUE)

## Get Data for Year 2015
final_data <- subset(fin_data, year =="X2015")
summary(final_data)

     geo                year             population        life.expectancy
 Length:195         Length:195         Min.   :8.030e+02   Min.   :49.60  
 Class :character   Class :character   1st Qu.:1.955e+06   1st Qu.:66.05  
 Mode  :character   Mode  :character   Median :8.320e+06   Median :73.30  
                                       Mean   :3.768e+07   Mean   :71.93  
                                       3rd Qu.:2.725e+07   3rd Qu.:77.50  
                                       Max.   :1.400e+09   Max.   :83.80  
                                                           NA's   :8      
     income         alpha.2            alpha.3           country.code  
 Min.   :   623   Length:195         Length:195         Min.   :  4.0  
 1st Qu.:  3270   Class :character   Class :character   1st Qu.:209.0  
 Median : 10800   Mode  :character   Mode  :character   Median :418.0  
 Mean   : 17179                                         Mean   :424.9  
 3rd Qu.: 24100                                         3rd Qu.:642.8  
 Max.   :120000                                         Max.   :894.0  
 NA's   :8                                              NA's   :21     
  iso_3166.2           region           sub.region        intermediate.region
 Length:195         Length:195         Length:195         Length:195         
 Class :character   Class :character   Class :character   Class :character   
 Mode  :character   Mode  :character   Mode  :character   Mode  :character   
                                                                             
                                                                             
                                                                             
                                                                             
  region.code     sub.region.code intermediate.region.code
 Min.   :  2.00   Min.   : 15.0   Min.   : 5.00           
 1st Qu.:  2.00   1st Qu.: 54.0   1st Qu.:11.00           
 Median : 19.00   Median :154.0   Median :14.00           
 Mean   : 71.74   Mean   :177.9   Mean   :14.89           
 3rd Qu.:142.00   3rd Qu.:202.0   3rd Qu.:17.00           
 Max.   :150.00   Max.   :419.0   Max.   :29.00           
 NA's   :21       NA's   :21      NA's   :119             

Plotly

scatter_plot <- plot_ly(
  data = final_data,
  x = ~income,
  y = ~life.expectancy,
  size = ~population,
  color = ~geo,
  text = ~paste("Country: ", geo, "<br>Population: ", population),
  type = "scatter",
  mode = "markers",
  marker = list(
    opacity = 0.6,  # Transparency level
    sizemode = "diameter",  # Set the size mode to diameter
    sizeref = 0.1,  # Adjust the size reference for better visibility
    line = list(
      color = "black",  # Boundary color for points
      width = 1  # Boundary width
    )
  )
)
layout <- list(
  title = "Association Between Life Expectancy and Income (Year 2015)",
  xaxis = list(title = "Income"),
  yaxis = list(title = "Life Expectancy"),
  showlegend = FALSE  # Hide legend for individual countries
)

# Combine the plot and layout
scatter_plot <- layout(scatter_plot, layout)

# Display the interactive scatter plot
scatter_plot